recode manual pages to UTF-8

[debhelper.git] / dh_installman

diff --git a/dh_installman b/dh_installman
index f054796ceabaaaee533cfa4d9e02e9e0fd034c55..55c573701d5f33af3b441f51584812ce892cbb17 100755 (executable)
--- a/dh_installman
+++ b/dh_installman
@@ -32,12 +32,17 @@ like .ll.8 and .ll_LL.8, or by use of the --language switch.
 If dh_installman seems to install a man page into the wrong section or with
 the wrong extension, this is because the man page has the wrong section
 listed in its .TH line. Edit the man page and correct the section, and
-dh_installman will follow suit.  See to L<man(7)> for details about the .TH
+dh_installman will follow suit.  See L<man(7)> for details about the .TH
 section. If dh_installman seems to install a man page into a directory
 like /usr/share/man/pl/man1/, that is because your program has a
 name like "foo.pl", and dh_installman assumes that means it is translated
 into Polish. Use --language=C to avoid this.
 
+dh_installman will use man to guess the character encoding of each manual
+page and convert it to UTF-8. If the guesswork fails for some reason, you
+can override it using an encoding declaration. See L<manconv(1)> for
+details.
+
 Any man page filenames specified as parameters will be installed into the
 first package dh_installman is told to act on. By default, this is the
 first binary package in debian/control, but if you use -p, -i, or -a flags,
@@ -143,35 +148,42 @@ foreach my $package (@{$dh{DOPACKAGES}}) {
        
                my $destdir="$tmp/usr/share/man/man$realsection/";
                my $langcode;
-               if (! exists $dh{LANGUAGE}) {
+               if (! defined $dh{LANGUAGE} || ! exists $dh{LANGUAGE}) {
                        # Translated man pages are typically specified by adding the
                        # language code to the filename, so detect that and
                        # redirect to appropriate directory, stripping the code.
                        ($langcode)=$basename=~m/.*\.([a-z][a-z](?:_[A-Z][A-Z])?)\.(?:[1-9]|man)/;
-                       if (defined $langcode && $langcode ne '') {
-                               # Strip the language code from the instname.
-                               $instname=~s/\.$langcode$//;
-                       }
                }
                elsif ($dh{LANGUAGE} ne 'C') {
                        $langcode=$dh{LANGUAGE};
-                       ($instname)=$basename=~m/(.*?)\./;
+               }
+               
+               if (defined $langcode && $langcode ne '') {
+                       # Strip the language code from the instname.
+                       $instname=~s/\.$langcode$//;
                }
                
                if (defined $langcode && $langcode ne '') {
                        $destdir="$tmp/usr/share/man/$langcode/man$realsection/";
                }
                $destdir=~tr:/:/:s; # just for looks
+               my $instpage="$destdir/$instname.$section";
 
-               if (! -e "$destdir/$instname.$section" && 
-                   ! -l "$destdir/$instname.$section") {
-                       if (! -d $destdir) {
-                               doit "install","-d",$destdir;
-                       }
-                       doit "install","-p","-m644",$page,
-                               "$destdir$instname.$section$gz";
+               next if -l $instpage;
+               next if compat(5) && -e $instpage;
+
+               if (! -d $destdir) {
+                       doit "install","-d",$destdir;
                }
-               
+               if ($gz) {
+                       complex_doit "zcat \Q$page\E > \Q$instpage\E";
+               }
+               else {
+                       doit "install","-p","-m644",$page,$instpage;
+               }
+               complex_doit "man --recode UTF-8 \Q$instpage\E > \Q$instpage.new\E";
+               doit "chmod",644,"$instpage.new";
+               doit "mv","$instpage.new",$instpage;
        }
 
        # Now the .so conversion.
@@ -205,6 +217,11 @@ sub find_so_man {
        }
        my $l=<SOTEST>;
        close SOTEST;
+
+       if (! defined $l) {
+               error("failed to read $_");
+       }
+       
        if ($l=~m/\.so\s+(.*)\s*/) {
                my $solink=$1;
                # This test is here to prevent links like ... man8/../man8/foo.8